Deep Learning

If you’re still buckled in to this rollercoaster of a ride that is, Thirty Days of Haydee, I thank you! Today is Day 2 so let’s get to it.. This morning, a good friend of mine (Love you P) sent me the pic above. A rainbow over a misty sky…

Vectors — The Machine Learning Perspective Vectors are commonly used in machine learning as they lend a convenient way to organise data. There’s almost no ML model where vectors aren’t used at some point in the project lifecycle. Often one of the very first steps in making a machine learning model is vectorizing the data. What is a Vector ? Physics…

Harnessing the Power of Dedicated DNN Training Chips — Part 3 — After much anticipation, Amazon EC2 TRN1 instances are now available for public use. Based on the AWS Trainium chip, the TRN1 instance type was specifically designed for accelerating deep learning training. This post is the third part of a series on training deep learning models on dedicated AI chips. In…

A demo of Galactica (named after Isaac Asimov’s Encyclopedia Galactica), a large language model (LLM) trained on 48 million scientific articles, was made available last week by Facebook’s parent company Meta. …

Author: Zifeng Wang (UIUC) — Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume a fixed table structure in training and testing. Before ML modeling, heavy data cleaning is required to merge disparate tables with different columns. This preprocessing often incurs significant data waste…

In this video, I show you how to use Amazon SageMaker to train a Transformer model with AWS Trainium and compile it for AWS Inferentia. Starting from a BERT model and the Yelp review datatset, I first train a multi-class classification model on an ml.trn1.2xlarge instance. I also show you…

Part II: Implementation Anomaly detection is one of the most widespread use cases for unsupervised machine learning, especially in industrial applications. In Part I, we motivated the use of variational autoencoders for this task and provided intuitive explanations of how to do it with references to dogs and sheep. In Part II, we…

Stablediffusion 2 has been released few days ago and it is accessible here: https://github.com/Stability-AI/stablediffusion Unfortunatly, the official documentation to make it works is complicated and.. it does not work except if you change few things that I explain here. Current installation recommandation Following screenshot is the current installation recommandations.